Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Offline multitask Reinforcement Learning on D4RL Antmaze medium-play

624Average Episodic Return

DiSPO

216.32322.16428533.84Mar 10, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.03
624
2024.03
397
2024.03
390
2024.03
370
2024.03
271
2024.03
264
2024.03
232